kurashigram

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden. It discloses that the output is a list with sources, which is some transparency, but it does not mention any constraints, limitations, or error behavior. For a tool with no parameters, this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with concrete examples, making it easy to parse and front-loaded with the core purpose. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters and no output schema, the description is fairly complete. It explains what the tool returns (a list with sources) and gives examples, but it could be clearer that it requires no input and returns a static list, especially given the many similar siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema fully covers parameter semantics (vacuously). The baseline for zero parameters is 4, and the description does not need to add parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns a list of today's answers to shopping questions, with examples and a mention of sources. It is specific about the resource and scope, though it doesn't explicitly differentiate from siblings like prices_now or cost_item that may overlap in function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus the many sibling tools. There is no mention of alternatives or conditions for selection, leaving the agent to infer based on the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses data freshness ('毎日更新' — updated daily), reliability ('推定なし' — no estimates), and the exact return format (item, per-unit cheapest, purchase link, normal price, date, source in one JSON). This is strong behavioral disclosure for an unannotated tool; only edge cases like unmatched queries are left unspecified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one dense, well-ordered paragraph: purpose front-loaded, then examples, output format, scope, and freshness/reliability. Every clause earns its place with zero filler or tautology.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by spelling out the full JSON return fields. Single parameter fully covered, scope and freshness disclosed. Minor gap: no guidance on out-of-scope or unmatched queries, but for a simple single-param tool this is not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents q. The description adds genuine value with three distinct query examples showing flexibility: standard form (一番安い水), inverted word order (トイレットペーパー安いの), and quantity specification (お米10キロ). It also ties the parameter to the output behavior, going beyond the schema's single example.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('一番安い〇〇を1回で答える' — answers the cheapest item in one go) with concrete query examples (一番安い水, トイレットペーパー安いの, お米10キロ). It defines clear scope (160 daily necessities + 52 home appliance types) which distinguishes it from sibling item tools like hikaku, super_item, and oroshi_item.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The examples and the phrase '1回で答える' (answer in one go) imply this is for direct single queries, and the scope statement (160 daily necessities, 52 home appliances) defines coverage. However, with numerous similar siblings (hikaku, cost_item, super_item, suii_item, lens_item), there is no explicit when-to-use vs. alternative guidance or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of behavioral disclosure. It provides meaningful methodological detail: data sources, starting year, index base, and the comparison method. It does not describe the output format or update cadence, but the key calculation behavior is transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, dense sentence that front-loads the core user question, then packs in sources, method, and target use cases. Every clause earns its place with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-parameter, no-output-schema tool with no annotations, the description covers purpose, data sources, methodology, and typical asks. It does not detail the exact response format, but that gap is minor given the tool's simplicity and the clarity of the description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so there is no parameter ambiguity. The schema is fully complete at 100% coverage, and the description adds contextual meaning about what the no-parameter request will answer.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description is a specific, question-led explanation: it compares the cash wage index from the Monthly Labour Survey with retail price item ratios over years, explicitly targeting real-wage questions. This clearly identifies the tool's function and distinguishes it from the sibling price/cost tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance: 'for consultations about real wages, whether life got easier, or whether salaries rose, use this.' It does not mention alternatives or when not to use it, but the usage context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It describes the output structure (per-flyer fields) but does not explicitly say whether this is a read-only query, whether it returns a list, or any operational limitations. The noun-phrase style ('値段') implies a lookup but never states the action or side-effect profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a compact Japanese sentence followed by a dense field enumeration and the valid chain values. The core purpose is front-loaded, and no irrelevant detail is included. The parenthetical list is somewhat heavy but still efficient for the information it conveys.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With only one parameter and no output schema, the description provides the key context by listing the returned fields per flyer, including item-level attributes. It is sufficient for an agent to understand the tool's result shape and invoke it correctly. Minor gaps remain around list shape, ordering, and error behavior, but these are less critical for a simple lookup.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, meaning the schema already documents the 'chain' parameter and its allowed values. The description repeats these values without adding new meaning, so it does not exceed the baseline for parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the resource: prices of flyers for one chain ('1つのチェーンのチラシの値段'), and enumerates the per-flyer fields returned such as publication period, store name, and item details. It distinguishes the tool by specifying 'one chain', but it does not explicitly name or differentiate from sibling tools like chirashi_index, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. It only states that 'chain' can be maruai, tamade, marudai, or kanesue, which is parameter enumeration rather than usage context. No exclusions or alternative tool references are provided, so an agent is left to infer when this is the right choice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does so thoroughly. It discloses that prices are human-read, includes both base and tax-included prices, specifies the exact tax verification formula (1.08, with 1.10 for alcohol and daily necessities), and explicitly states '推定なし' (no estimates). This gives an agent strong expectations about data provenance and quality.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences with no filler. The core subject and resource type are front-loaded, followed by concrete chain names and validation details. Every sentence adds meaningful information, and the structure is easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with no output schema, the description does a good job of explaining what the returned list contains and its coverage. It names all included chains, specifies the price types, and defines validation rules. It could be slightly more complete about output formatting or update behavior, but nothing critical is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is empty, so there are no parameter semantics to explain; the baseline of 4 applies. The description provides useful context about what data fields are present (chain, prefecture, period, item count, prices), compensating for the absence of a structured schema without needing to explain specific parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as providing a list ('一覧') of actual supermarket selling prices read from official flyers, including chain, prefecture, publication period, and item count. It names specific chains and validation criteria, making the resource distinct. However, it does not explicitly differentiate itself from sibling tools like chirashi_chain, so it stops short of full clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool—when you need verified price data from these named regional supermarkets—but gives no explicit guidance on when to prefer an alternative. With many sibling tools in the same domain, the lack of any 'use this instead of X' or exclusion criteria is a notable gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the full burden of behavioral disclosure. It reveals that the tool returns survey prices for the latest month and monthly history, and specifies the data source and number of cities. However, it omits details about error handling for invalid codes, output structure, or any side effects. This partial disclosure earns a mid-range score.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loading the core purpose and then adding necessary details (source, item count, time range, and code examples). Every piece of information is relevant, and there is no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there is no output schema, the description partially explains what will be returned: survey prices for ~550 items with latest month and monthly history. However, it does not specify the exact output structure (e.g., whether it returns a list, a summary, or time-series format), nor does it address edge cases like invalid codes or unsupported cities. This leaves some ambiguity for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides only '5桁の自治体コード' for the 'code' parameter. The description enhances this by explaining the code is a 5-digit national local government code and provides concrete examples (Sapporo 01100, Tokyo wards 13100, Fukuoka 40130). This adds meaningful context beyond the schema, clarifying the format and usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides cost-of-living data for 81 Japanese cities, sourced from a specific government survey, covering ~550 items with latest month and monthly history. It explicitly describes the resource (city-level price data) and the scope, making it distinct from sibling tools like cost_item or cost_index which likely focus on individual items or indices.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide any guidance on when to use this tool versus alternatives. It merely states what the tool does, leaving the agent to infer selection criteria. There is no mention of preferred use cases, exclusions, or conditions that would route to a different sibling tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It implies a read-only data retrieval operation with no side effects, but it does not explicitly state this, nor does it mention any potential limitations, data source, or update frequency. It is adequate for a simple list operation but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that front-loads the main content (items, fields, cities, latest month) with no wasted words. It is appropriately sized and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (zero parameters, no output schema), the description covers the essential content: the list of items with specified fields, city list, and latest month. It could mention the output format, but for a list retrieval tool, this is sufficient. It is complete enough for an agent to understand what it returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and an empty schema, so there is nothing to document. According to the baseline for 0 parameters, this scores a 4; the description does not need to add parameter meaning since there are none.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the resource (daily living expense items with fields like code, name, English name, unit, category) and the action (list), also mentioning city list and latest month. It is not a tautology and provides specific content, but it does not differentiate this tool from siblings like cost_item or cost_city, which may have overlapping purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus the many sibling tools (e.g., cost_item, cost_city, data_catalog). It does not mention any context, exclusions, or alternatives, leaving the agent to infer usage from the content alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden and does a good job by specifying what data the tool exposes: an 81-city list sorted by cheapest price, monthly national medians, and per-city history. It does not describe output shape, update frequency, or access constraints, so it falls short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and information-dense: purpose, data contents, parameter guidance, and sibling routing are each covered without filler. The core scope ('1つの品目') is front-loaded, and the cost_index pointer is placed at the end where it can redirect without obscuring the main purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter lookup with no output schema and no annotations, the description is largely sufficient: it names the data views, gives code examples, and routes list requests to a sibling. It could be more complete by describing the return format or date coverage, which is why it is not a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents 'code' as 品目コード4桁 with 100% coverage, so the baseline is 3. The description adds value by giving real examples (1303, 3001, 7301) and making the mapping from code to item explicit, though it does not enumerate all valid codes.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with '1つの品目の都市別の調査価格', clearly identifying the resource and scope: survey prices for one item across cities. It then enumerates the specific data views returned — the latest 81-city list, monthly national median, and per-city history — and ends with '一覧は cost_index で', which distinguishes it from the sibling list tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes the appropriate usage context clear: use this for single-item city price detail, national medians, and history, and explicitly sends list-ranking requests to cost_index. Concrete code examples (牛乳 1303, 民営家賃 3001, ガソリン 7301) further guide invocation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the tool's behavior well for a parameterless read-only catalog: it returns a listing of all published datasets ('一覧'), and it defines the content scope (numbers, primary sources, methodology). The word '公開している' implies public data with no side effects. It does not describe output formatting or pagination, but for a 0-parameter reference tool these gaps are minor.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two tight sentences: the first names what the tool is, the second explains the catalog's contents and when to use it. Every clause earns its place, and the core purpose is front-loaded. No filler, no redundancy with the empty schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a low-complexity tool (0 params, no output schema, no annotations), the description is nearly complete: an agent knows what it will get (a list of all datasets), what information that list contains (numbers, sources, methodology), and when to invoke it (before citing). The only missing piece is a concrete description of the return format, but '一覧' (list) already hints at it, and nothing critical is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 properties, so per the rubric the baseline is 4. There are no parameters to document, and the description still adds value by clarifying what the tool returns (the full dataset listing) without requiring any arguments. Nothing more is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource and action: '暮らしグラムが公開している全データセットの一覧' (a list of all datasets published by Kurashi Gram). The word '全' (all) makes clear this is the meta-index covering every data tool, which inherently distinguishes it from the individual sibling data tools (answers, cheapest, gov_money, etc.). It also specifies what the catalog contains: which numbers, from which primary sources, and how they are produced.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides an explicit usage trigger: '引用する前にここを見る' (look here before citing). This tells the agent when to consult this tool. However, it does not name alternatives or state when not to use it, so it stops short of a full when/when-not specification.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the burden. It usefully discloses the data source (Amadeus), the acquisition date, and fixed query conditions (one-way, adult, direct). However, it does not state whether the data is a live query or a static snapshot, nor what output shape to expect, leaving some behavioral ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact sentence with every clause carrying information: route count, fare type, time horizons, passenger type, direct-flight constraint, source, and date stamp. It is front-loaded with the core 'ledger' concept and has no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless tool this is close to complete, but it never specifies the output format or fields of the ledger. It also omits the actual route list and whether the data is refreshed daily or per request. Given the absence of an output schema, a short note on return structure would make it fully self-contained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so the schema fully defines the input surface (empty object). The description adds context about the fixed criteria (routes, date horizons, passenger type), which is helpful even though no parameter documentation is needed. Baseline for zero-parameter tools is 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the tool as a ledger of the cheapest one-way direct fares for 18 Japanese domestic routes, with explicit time horizons (tomorrow/1 week/1 month) and adult traveler. This differentiates it from sibling tools like 'cheapest' or 'hikaku' by specifying the domain and scope. It lacks an explicit verb like 'returns' or 'lists', but the noun phrase '台帳' and the specificity make the purpose clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance about when to choose this tool over siblings such as 'cheapest' or 'hikaku', nor any exclusion criteria. The description implies a read-only data reference for domestic flight fare comparisons, but an agent must infer this. With many sibling tools, the lack of routing guidance is a clear gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It does reveal the sorting criterion and the slug's genre-filtering role, but it does not mention return shape, empty results, error behavior, or whether the data source is live. This is adequate but not deeply transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: it states the tool's purpose first, then defines the one required parameter, and finishes with a pointer to the index sibling. Every clause earns its place and there is no redundant filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple lookup tool with one required slug parameter, the description covers the core call: what is returned, the sort ordering, the parameter's meaning, and where to get the full list. It is slightly incomplete in not clarifying the exact columns or units implied by '量', but it is still nearly sufficient for an agent to call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides only a bare 'slug' string with no description, so the description's explanation that the slug is the genre in English letters such as hotate, unagi, and kani adds substantial semantic value. It compensates well for the 0% schema coverage, though it does not provide an exhaustive list of valid genre slugs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the output: a comparison table of furusato tax return gifts, sorted by amount per 10,000 yen donation. It also specifies the role of the slug (genre in roman letters) and distinguishes itself from furusato_index by pointing there for the list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for use: provide a genre slug like hotate or unagi to get the sorted comparison table. It also routes list-style requests to furusato_index, providing a useful alternative, though it does not explicitly discuss when to choose this over the other furusato siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description does not disclose any behavioral traits such as read-only nature, potential side effects, rate limits, or output characteristics. The description only hints at data content without saying what happens when called.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short, which is superficially concise, but it is under-specified to the point of being unhelpful. It lacks necessary details and front-loads a vague subject instead of a clear call to action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, no annotations, and minimal parameter documentation, the description fails to provide the necessary context for an agent to call this tool correctly. Even a single-parameter tool needs to clarify input semantics and expected output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The sole parameter 'slug' is completely undocumented in the schema (0% coverage). The description does not explain what 'slug' refers to (e.g., genre identifier, item ID) or its format, leaving the agent to guess.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description is a noun phrase describing content ('Daily time series of genre – median and p90 of quantity per 10,000 yen') with no explicit verb or action. It is unclear whether the tool retrieves, computes, or lists this data. It also does not distinguish itself from the many sibling tools (e.g., furusato_index, furusato_hitorigurashi) which likely also deal with time-series or genre data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus its siblings. Given the large sibling list, an agent has no clue about the intended context or selection criteria, making it impossible to route correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the full behavioral burden. It discloses the filtering logic (2kg or less), the sorting order (descending by content per 10,000 yen), and the data source (reading from product names, excluding unreadable ones). It doesn't mention error handling or no-result behavior, but the core behavior is transparent. A small gap remains regarding what happens when no items match.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact, using one sentence with clear clauses. It front-loads the purpose and immediately provides usage criteria. Every clause adds value: filtering, sorting, data extraction rule, and usage triggers. No redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a filter-and-sort tool with no output schema, the description is fairly complete: it defines what it filters, how it sorts, and when to use it. It could specify whether results are limited or how many items are returned, but given the tool's simplicity, this is a minor gap. The description covers the essential context an agent needs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so there is no schema to describe. The baseline for 0 params is 4. The description implicitly defines the query scope via keywords, but since no parameters exist, no additional parameter semantics are needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: it filters furusato nozei return gifts for single-person households, limits to 2kg or less, and sorts by content amount per 10,000 yen. It also provides specific usage triggers ('一人暮らし', '少量', etc.), distinguishing it from generic furusato tools. This is specific and actionable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use this tool: for consultations involving 'living alone', 'small amount', 'amount you can eat', or 'one person'. It doesn't name alternatives, but the trigger phrases effectively route the agent to this tool over siblings like furusato or furusato_index.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states that this is a genre list; it does not disclose whether it returns a static list, whether it requires any parameters, what the output format is, or whether it performs any side effects. For a simple list tool this is a moderate gap, but the lack of any behavioral context beyond the noun phrase is thin.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short phrase, which is appropriately concise for a zero-parameter list tool. It is front-loaded with the key resource ('ふるさと納税') and the type of output ('ジャンル一覧'). It could be slightly improved by adding a verb, but it is not bloated or redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, no-output-schema tool, the description is minimally adequate: it tells the agent what the tool is about. However, it does not state the return format, whether it is a simple static list, or how it relates to sibling tools like furusato or furusato_history. Given the large sibling set, a bit more context would help an agent select it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and schema description coverage is 100% (vacuously, since there are no properties). The description does not need to explain parameters because there are none. Baseline 4 for zero-parameter tools is appropriate; the description's mention of 'genre list' clarifies what the tool returns without needing parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'ふるさと納税のジャンル一覧' (Furusato tax genre list) states a specific resource (genre list for furusato tax) and a clear noun phrase, but it lacks a verb. It is distinguishable from siblings like furusato, but the lack of an explicit action (e.g., 'get', 'list') makes it slightly less clear than a full verb+resource statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus alternatives. The description does not mention any conditions, exclusions, or related sibling tools. An agent must infer that this is the index/list tool for furusato tax genres based on the name and description alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden. It discloses what kind of content is returned (amount, target, deadlines, procedures, pitfalls), the provenance (primary ministry sources), and the acquisition date. It does not mention error behavior or exact return shape, but it gives solid context beyond the bare schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense sentence that front-loads the core purpose, then gives concrete examples, and ends with routing to the sibling list tool. Every clause earns its place; no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given one required parameter, no output schema, and no annotations, the description explains the resource, its content categories, and the source for valid slugs. It could add response shape or invalid-slug behavior, but the essential calling context is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It provides example slug values and hints that valid slugs correspond to program identifiers, but it does not define the slug format, how to discover all valid slugs, or whether slug must come from the gov_money list.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly defines the tool as returning details for a single government program: amount, eligibility, deadlines, procedures, and pitfalls, with source and acquisition date. It also differentiates itself from the sibling gov_money by explicitly saying that the list is obtained via gov_money.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly directs users to gov_money for the list of programs, which implies using this tool when a specific program slug is already known. However, it does not elaborate on when not to use this tool or compare with other siblings like gov_pref.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavior. It mentions the source (ministry primary materials) and that data includes an acquisition date, which hints at freshness and reliability, but it does not describe the output format (e.g., list, summary), whether it is read-only, or any limitations. For a tool with zero annotation coverage, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact sentence that front-loads the main topic (government and money) and then enumerates specific examples. It is concise without unnecessary words, but it packs multiple items into one sentence, which could be slightly clearer with a list structure. Overall, it is well-sized and focused.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that there are no parameters and no output schema, the description should provide enough context for an agent to understand what the tool returns. It states it provides amounts and deadlines for several categories, but it is vague about the exact scope (the 'etc.' and the lack of detail on how the data is presented). It is adequate for a simple lookup tool, but it could be more complete by stating whether it returns a single value or a table, and how the acquisition date is used.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema covers everything. The description does not need to explain parameters. The baseline of 4 is appropriate because there is nothing to add; the description correctly does not attempt to explain non-existent parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool's focus: government-related financial information (high-cost medical care, child allowance, death procedures) with amounts and deadlines. It names specific topics and the type of data provided, distinguishing it from generic government guides. However, it lacks an explicit action verb like 'retrieve' or 'list', making the purpose slightly less direct than ideal.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus siblings such as gov_guide or gov_pref. It does not state any exclusions, alternatives, or conditions. An agent would have to infer that this tool is for financial amounts and deadlines, but there is no explicit differentiation from other government-related tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the data is limited to what is confirmed from official primary sources and that output includes a 2-digit prefecture code, which are useful constraints. However, it does not state whether the operation is read-only, the return format beyond the code, or any other behavioral traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact sentence with no redundancy. It conveys the core resource, a source constraint, and an output detail efficiently. There is no waste, and the essential information is immediately accessible.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no parameters and no output schema, the description provides some context: what it covers, source criteria, and an output hint. However, it lacks clarity on the exact structure of the returned data (e.g., a list of benefits per prefecture, fields beyond the code), which an agent would need to know to interpret results correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and schema coverage is trivially 100%. Baseline for zero parameters is 4, and the description does not need to explain parameters. The mention of '県コード2桁つき' pertains to output, not input, so it adds no parameter semantics but does not detract.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource as prefecture-specific benefits and support systems, and notes a source constraint (official primary sources) and an output hint (2-digit prefecture code). It distinguishes itself from siblings like gov_guide and gov_money by its specific focus on prefecture-level benefits, though it lacks an explicit verb like 'list' or 'retrieve'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool over its siblings. It does not mention alternatives like gov_guide or gov_money, nor does it state conditions for selection. The context is implied but not explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations and no output schema, the description carries the burden of explaining behavior. It does so by disclosing that the tool uses a fixed six-item basket across 81 cities and produces a monthly cost figure, which is meaningful behavioral transparency for a zero-parameter read-only comparison tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, dense sentence that front-loads the core action ('市をくらべる') and then efficiently supplies method, scope, and typical user intents. No wasted words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-parameter, no-output-schema tool, the description sufficiently covers what the tool does and when to use it. It could be more explicit about how results are presented (e.g., ranked list, all 81 cities), but the core decision-making context is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and the schema coverage is essentially complete. The description adds value by defining the basket contents and the unit of comparison (monthly cost), satisfying the baseline of 4 for parameter-free tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('くらべる') and resource ('81市'), and explains the comparison method: applying a fixed basket of items (rent, rice, eggs, milk, bread, electricity) to compute monthly costs. This distinguishes it from sibling city/cost tools by clarifying it compares cities with an identical basket.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear use cases: '引っ越すといくら変わる' and 'どの街が安い' consultations. It does not explicitly name alternative tools or when-not-to-use, so it falls short of a full 5, but the use context is strongly implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It discloses data sources (気象庁), update frequency (10分ごと), time window (直近7日), and geographic scope (県ごと). It does not disclose output format, whether it returns both warnings and earthquakes together, or any rate limits. The disclosed traits are useful but not comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact sentence that packs in source, update frequency, time window, and geographic granularity. It is front-loaded with the main subject. Slightly dense due to the colon and parentheticals, but every element adds information. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, no-output-schema tool, the description covers the main query intent: current warnings and recent earthquakes. It doesn't specify the exact output structure (e.g., list vs. object, units, coordinate format), but with no schema or output schema, an agent can still call it correctly since there are no inputs. The main gap is not stating whether both data types are always returned together or how to interpret the results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, so the schema provides no parameter semantics. The description compensates by explaining what data is returned and its scope. With no parameters to document, a baseline of 4 is appropriate because the description fully clarifies what the tool does without needing parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides current Japan weather warnings/advisories (by prefecture, every 10 minutes) and recent 7-day earthquake data (intensity, epicenter, coordinates). The verb is implicit but the resource and scope are specific. It doesn't explicitly differentiate from siblings, but the domain (Japan weather/earthquakes) is distinct enough among the listed siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage: when you need current Japan warnings or recent earthquake info. It doesn't explicitly state when not to use it or name alternatives, but the context is clear enough for an agent to select it for weather/seismic queries. No exclusions or alternative routing are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it provides substantive scope: data comes from the Ministry of Finance, is daily, covers 10-year and 1-year JGB yields, and spans from 1974 onward. It does not disclose units or the exact return shape, but it is far beyond a bare label.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences convey source, maturities, frequency, start date, and intended use with no redundant detail. The topic is front-loaded and every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-parameter data tool with no output schema, the description is complete: it states what data, from whom, at what frequency, since when, and for what purpose. The absence of explicit units or response format is minor given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and the schema is empty, so the baseline is 4; there are no parameter semantics for the description to add. The description instead clarifies the data content, which is useful context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as a source of Japanese Ministry of Finance government bond yields, specifying 10-year and 1-year maturities, daily frequency, and a start year of 1974. It is not a tautology, but it lacks an explicit action verb and does not contrast with sibling tools such as chingin or hikaku.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The closing phrase '住宅ローンや預金金利の背景' gives a concrete usage context: the data is relevant as background for mortgage and deposit rate questions. It does not, however, name alternatives or state when not to use this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses important methodology: 79 months of survey prices, removal of price-increase effects, and isolation of monthly patterns. This is meaningful behavioral context beyond a simple 'returns seasonal calendar'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: the first sentence states the core question, the second defines the resource, and the third adds methodology and usage context. Every sentence earns its place without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with no output schema, the description provides sufficient context about what the tool answers, how it was computed, and when to use it. It does not describe the exact return format, but the purpose and domain are clear enough for the agent to invoke it appropriately.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description adds conceptual meaning by explaining that the calendar works per product category ('品目ごと') and is derived from detrended monthly data, which helps an agent understand its scope even with no explicit input schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies what the tool does: it answers which month is cheapest for a given item and presents a seasonal buying calendar by product category. It also distinguishes itself through its seasonal/monthly pattern focus, though it does not explicitly name sibling alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use it: for consultations about 'vegetables being cheap', 'seasonality', and 'good time to buy'. It does not provide exclusions or mention alternative tools, but the use case is clear enough for an agent to route to it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden. It does disclose the cost calculation source (Rakuten same-day cheapest unit prices) and unit (per serving, yen), which is useful. But it does not state how the result is presented, whether the content changes daily, or whether costs are estimates.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one compact sentence with the core purpose front-loaded and no filler. Every clause contributes: budget, daily menu, ingredient constraint, and cost derivation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with no output schema, the description covers the essential expectations: a daily menu, a 500-yen budget, shelf-stable recipes, and a per-serving cost from Rakuten prices. It does not specify the exact response structure or the date dependency, but nothing critical is missing for making a first call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so there are no parameter semantics to clarify and the schema fully covers this. The description still adds useful context about the cost unit, though it defines no arguments.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific resource: a 500-yen daily menu, with recipes using shelf-stable ingredients and per-serving cost calculated from Rakuten prices. It is distinct enough from price/cost-focused siblings like cheapest and cost_item, though it lacks a clear tool verb such as 'returns' or 'generates'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The usage context is implied: this is for today's 500-yen menu and its ingredient cost. However, it gives no explicit guidance about when to choose it over alternatives, no prerequisites, and no exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the behavioral burden. It adds useful context: the tool checks Rakuten and Yahoo! Shopping daily, and treats same-diameter/same-model items as equivalent. However, it does not disclose return format, read-only status, or edge-case behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, each contributing useful information: the purpose, the data source, and parameter semantics. The main purpose is front-loaded and there is no redundant filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter lookup with no output schema, the description covers what the tool searches, how to supply the diameter, and how results should be compared. It does not describe the response shape, but the agent has enough information to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100% for 'dia', so the baseline is 3. The description adds concrete examples (67, 77, 52) and clarifies that dia is a numeric diameter, not a product code, which goes beyond the schema's 'フィルター径（mm）'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns 'レンズフィルターのきょうの最安値' and scopes it by filter diameter, specific filter types, and marketplaces. It is easy to tell apart from the lens_* siblings in general, though it does not explicitly name an alternative tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives input guidance ('dia はフィルター径の数字') and a comparability note, but it does not state when to prefer this tool over sibling tools, nor when not to use it. No exclusions or alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the behavioral burden. It discloses data provenance and freshness ('毎日調べた値・推定なし') and implies a read-only lookup through '台帳', but it does not explicitly state read-only behavior, authentication needs, or response shape. This is adequate but not comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: the core resource and scope appear first, followed by data details and the mount instruction. Each sentence adds necessary information with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter index tool, the description covers what data is returned (per-lens cheapest prices and specs) and its source. However, with no output schema and no annotations, it omits response structure, pagination/list-size behavior, and the effect of omitting the optional mount parameter, leaving some ambiguity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema gives only a bare 'mount' string with 0% description coverage. The description adds meaning by specifying 'mount は sony-e', giving the expected value and tying it to the mount-based scope. It leaves optionality and other possible mount values unstated, but it substantially compensates for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the tool as a ledger/index of interchangeable lenses ('交換レンズの台帳'), scoped by mount and initially Sony E, and states its contents: per-lens daily lowest prices from Rakuten and Yahoo! Shopping plus key specs. This is clear, but it lacks an explicit verb and does not name sibling tools to distinguish it from lens_item or lens_filter.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides input guidance through 'mount は sony-e' and scoping via 'マウント別・まずソニーE', which tells the caller the current supported mount. However, it never states when to prefer this tool over siblings such as lens_filter or lens_item, so the usage guidance is only implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden. It does disclose data sources and freshness ('today's cheapest price') and lists returned content, but it does not state read-only behavior, auth needs, error handling, or what happens when no data exists. The description is informative but not fully transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short Japanese sentences cover output content, data sources, parameter provenance, and an example with no fluff. The output description is front-loaded and the slug note is placed exactly where it is needed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only lookup with only one required parameter, the essentials are present: what data is returned and how to obtain a valid slug. However, no output schema exists and mount is undocumented, so return format and the optional parameter behavior remain open questions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage, the description must document parameters itself. It explains slug's provenance and gives an example, but the optional mount parameter is completely undocumented. This leaves one of two parameters semantically unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description precisely identifies the tool's data product: today's lowest price (Rakuten/Yahoo!), daily history, and specs for a single interchangeable lens. It also distinguishes this from index-level siblings by stating the slug comes from lens_index and giving a concrete example.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'slug は lens_index の slug' implies a workflow of first getting a slug from lens_index, but it never states when to prefer lens_item over lens_index or any other sibling. Usage context is present but left to inference, with no explicit when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it does well: it discloses data provenance (values checked daily on Rakuten Market and Yahoo! Shopping), the computation basis, sorted output, and the 'no estimates' (推定なし) qualifier, which is meaningful for a price tool. It omits output-shape details, but the read-only, computed-report nature is clear.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four compact sentences with the core purpose front-loaded. Every clause earns its place: scope, sort order, data source, and the estimation policy. No filler, no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 0-parameter tool with no annotations and no output schema, the description covers purpose, scope, ordering, data source, and a transparency guarantee—nearly everything an agent needs to invoke it correctly. The only gap is that it does not describe the returned fields, which matters a bit more because no output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description adds the semantic context an agent needs to interpret this fixed report: scope (6 mounts, two marketplaces), sort order, and the price-drop threshold it tracks.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource: a list (一覧) of interchangeable lenses whose price fell below the previous best price, computed across six mounts. It adds the sort criterion (drop amount, descending) and the data basis, which together clearly distinguish it from the lens siblings (lens_filter, lens_index, lens_item).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The use context is implied rather than explicit: an agent can tell this is the tool for 'which lenses got cheaper' queries, but the description never names alternatives or states when not to use it. With four lens-related siblings (lens_filter, lens_index, lens_item) and pricing tools like hikaku and prices_now, explicit routing would materially help.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and adds meaningful behavioral context: it says the data is verified from official pages, limited to tax-included regular prices (excluding discounts), and refreshed weekly. These are real caveats beyond what the name or schema express, helping an agent judge freshness and scope before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact Japanese sentence that front-loads the topic, then packs the essential constraints and field list without wasted words. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless, read-only data lookup tool, the description is largely complete: it states the subject, geographical scope, source reliability, price type, update frequency, and available fields. It lacks only explicit routing guidance to sibling tools, but that is already covered under usage guidelines.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so the baseline is 4. The description adds value by listing the data fields an agent can expect (company, plan, GB, monthly yen), which partially compensates for the absence of an output schema, even though there are no parameters to document.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource: Japanese mobile phone rate data, with explicit scope ('official pages', 'tax-included regular rates only') and expected fields (company, plan, GB, monthly yen). It is more specific than the tool name alone and implicitly distinguishes itself from sibling tools like hikaku or cheapest by emphasizing 'regular rates only', though it does not explicitly name any alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus siblings such as hikaku, cheapest, or chingin. The description states data constraints (official, tax-included, weekly-checked) but does not explain when an agent should select mobile_plans over alternatives or when it should not.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry behavioral context; it does indicate the tool is a read-only listing operation and mentions that it uses the same key as kuongeo.com's /api/here. However, it does not disclose error behavior, rate limits, or whether valid codes are required, leaving some behavioral ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loads the core function and code format. The second clause about the shared key is useful but somewhat cryptic, so the text is concise without being perfectly polished.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple (one parameter, no output schema), and the description covers the main purpose and parameter. Still, it does not describe the structure of the returned list, possible empty results, or error cases, and it gives no context for choosing this tool among many siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema only defines 'code' as a string with no description, but the tool description adds that it must be a 5-digit municipality code (自治体コード5桁). This is the essential semantic for the single parameter, though it does not give examples or format details such as leading zeros.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states that the tool returns the list of return gifts (返礼品) for a municipality identified by a 5-digit code. This is a clear resource-and-output statement, though it lacks an explicit verb and does not differentiate from related siblings like furusato.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to use this tool instead of a sibling, and no alternatives or exclusions are mentioned. The only usage hint is implied by the purpose: use it when you have a 5-digit municipality code and need its return-gift list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It discloses the key scope: yearly averages, unit, time range, and data source. However, it does not describe the return format or edge-case behavior, so it is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact Japanese sentence with no filler. It front-loads the primary query and appends the time range and source succinctly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with no output schema, the description is fairly complete: it states the data type, unit, period, and source. It omits only display or formatting details, which are not critical for this simple lookup.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so there is nothing for the description to document beyond the schema. The baseline 4 applies because no parameter-semantics burden exists.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific resource: annual average crude oil prices in dollars per barrel from EIA since 1986. The question phrasing clearly conveys the lookup intent, and the domain is specific enough to distinguish it from sibling tools like nagai_fx.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear context for when to use the tool: when the user asks about historical crude oil prices in dollars per barrel by year since 1986. It does not explicitly name alternatives or exclusions, but the unique domain makes the usage obvious.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries behavioral disclosure. It states the exact data source (European Central Bank), the granularity (annual averages), and the period (from 1999), which meaningfully describes what an agent can expect. It does not mention output format or currentness, but for a parameterless read-only lookup this is a reasonable disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact sentence that front-loads the core question, then adds the data range, source, and intended trigger. Every part earns its place and there is no redundant restatement of schema or title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple parameterless tool with no output schema, the description supplies the essential context: what question it answers, the data source and period, and when to use it. A bit more detail about the return shape would be nice, but it is not a serious gap given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline of 4 applies and there is no parameter documentation burden. The description usefully clarifies the fixed scope of the query: yearly averages since 1999, which is sufficient to invoke the tool correctly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies what the tool provides: historical USD/JPY annual average exchange rates from 1999 onward, sourced from the European Central Bank. The FX focus distinguishes it from siblings like nagai_crude and prices_now, though it does not explicitly name alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The final clause, '物価が上がった背景を聞かれたときに' ('when asked about the background of price increases'), gives an explicit trigger context for using the tool. It does not state when not to use it or point to specific sibling tools, but the intended use case is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the burden. It discloses the data source (Rakuten), update cadence (daily), and normalization basis, which is useful behavioral context. However, it does not mention the response shape, pagination, or error behavior, and it does not explicitly state that the operation is a read-only lookup.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: the core meaning (daily unit prices of daily necessities) comes first, followed by parameter guidance and a pointer to the index tool. Nothing is filler, though the single run-on sentence could be slightly better structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter read tool with no output schema and no annotations, the description covers source, frequency, normalization, slug examples, and the sibling index tool. It does not describe the return format, but that is a minor omission given the low complexity and clear data semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates by giving concrete slug values (toilet-paper, tissue, diaper-pants, laundry-detergent, water, rice) and directing the agent to nichiyo_index for the full list. It does not exhaustively enumerate valid slugs or specify slug format rules, but for a single required parameter this is sufficient guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as a daily listing of unit prices for daily necessities from Rakuten, normalized to per-roll/per-sheet/100ml/per-kg. It is unambiguous about the resource, though it does not explicitly contrast with other price-related siblings such as cheapest or hikaku; it only points to nichiyo_index for the broader list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool: when you need unit prices for daily necessities identified by a slug, with example slugs provided. It also tells the agent to use nichiyo_index for the catalog/list, which is a form of alternative routing, but it gives no explicit conditions for avoiding this tool or choosing among the many sibling price tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the content returned (list and median) and does not mention whether the operation is read-only, how 'that day' is determined, what units or format are used, or any other behavioral traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence with no filler or repetition. It front-loads the core output content and is appropriately sized for a zero-parameter tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is minimally viable: an agent learns the tool returns a list of daily necessity terms and a median value. However, with no output schema and no annotations, it omits what the median refers to, the expected output shape, and how this tool relates to similar siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so there is nothing for the description to explain about parameter semantics. The baseline of 4 applies because no parameter documentation is needed; the description's reference to 'that day' is not a parameter but an implicit context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource: a list of daily necessity terms and the day's median value. It conveys the tool is a data-retrieval/index lookup, though it lacks an explicit verb. It does not differentiate itself from the sibling tool 'nichiyo'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus siblings such as 'nichiyo', 'prices_now', or 'cost_item'. No conditions, exclusions, or alternative recommendations are provided, leaving the selection decision largely to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and largely delivers: it discloses data provenance (東京都中央卸売市場の日報), update cadence (毎日読み取り), units (1kgあたり・消費税込み), and the comparison baseline (農林水産省の全国470店調査). It does not describe the output shape or explicitly confirm read-only behavior, but the data-source and scope disclosure is unusually substantive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The entire definition is one dense sentence with every clause carrying information, and the core purpose is front-loaded. Readability would improve by splitting it into two sentences, but there is no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with no output schema, the description gives an agent enough context to know what will be returned and from which sources. Minor gaps remain — the concrete item coverage and how 'today' is determined — but nothing blocks correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description compensates for the empty schema by explaining exactly what values come back: per-kg tax-inclusive wholesale prices alongside the national retail average and the resulting multiplier. No parameter-level clarification is needed since there are no parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource and question: how much vegetables and fruits traded today in Tokyo's wholesale market (1kg, tax incl.), read from the Tokyo Metropolitan Central Wholesale Market daily report. It clearly states the tool's function and the retail-comparison angle. However, it does not differentiate itself from the sibling oroshi_item, which presumably covers item-level wholesale lookups.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied rather than stated: an agent can infer this tool answers 'what are today's wholesale prices for veggies/fruit in Tokyo' and shows the wholesale-to-retail multiplier ('市場から店までで何倍になるかが分かる'). But there is no explicit when-to-use or when-not-to-use guidance, and no alternative tool is named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context: per-kg pricing, market-specific values, and daily movement. However, it does not explain return shape, date handling, units of currency, or behavior for invalid slugs, so the transparency is adequate but not deep.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences with no filler. The first sentence states the core output and unit, and the second gives parameter guidance and points to the list tool. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter lookup with no annotations and no output schema, this description covers the essential context: what the tool returns, the per-kg unit, the market/daily dimension, and how to find valid slugs. Minor omissions like exact output structure and explicit when-to-use conditions are not severe for this tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema only defines slug as a required string with no description. The tool description compensates by listing valid slug examples such as cabbage, daikon, onion, and recommending oroshi for the complete list, which gives the agent a concrete way to discover valid values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource: one item's wholesale price per kg, with market-level detail and daily movement. It distinguishes itself from the sibling tool oroshi by indicating that oroshi is the list. It lacks an explicit action verb such as '取得する' or '表示する', but the meaning is still concrete and specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides direct routing guidance by stating '一覧は oroshi で', which tells the agent to use oroshi for the full list of slugs. It does not discuss alternatives like super_item or cost_item, but for its most closely related sibling the guidance is explicit and useful.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry behavioral context. It does disclose data sources (agency and ministry) and update frequency (weekly), which is useful. However, it doesn't clarify whether the tool returns a single value or a series, or whether it requires a specific date. The description is sufficient for a simple lookup but lacks depth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact sentence that packs in the key information: commodities, data sources, geographic scope, and update frequency. No wasted words. It is front-loaded with the main items first.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with no output schema, the description is quite complete. It tells the agent exactly what data is available and the source. Missing details like the exact units (e.g., yen per liter, yen per 5kg) are minor and likely implied. However, it doesn't explain how to access historical data or nuance about the POS data, but those may be out of scope.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the description is the only source of semantics. It fully explains what the tool returns without parameters. The coverage is 100% because there are no parameters to document, but the description adds value by specifying the exact data (gasoline and rice) and sources.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states what the tool reports: current prices for gasoline (weekly, from a named agency, across 47 prefectures) and rice 5kg (from a named ministry, POS data, weekly). This distinguishes it from generic price tools, though it doesn't explicitly contrast with siblings like 'super_pos' or 'cost_item'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the use case: get current prices for these specific commodities. It doesn't explicitly state when to use this versus alternatives, but the specificity of the items and data sources suggests it is for current prices rather than historical or index data. No exclusions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the data source, geographic scope (81 cities), aggregation method (median), time granularity (monthly), and the 5-year multiplier angle. It does not describe the output format or any refresh/limitation details, but for a zero-parameter read-only data tool these are minor omissions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded with the core question it answers, then packs source, scope, granularity, use cases, and the sibling distinction into a single dense sentence with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no parameters, no output schema, and low invocation complexity, the description covers all essentials: what is computed, from which data source, at what granularity, and when to prefer it over its sibling. Nothing needed to select or call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters and an empty input schema, so the baseline is 4. The description adds context by indicating that the tool is pre-scoped to aggregate monthly medians for 81 cities, which explains why no user-supplied parameters are needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource and purpose: it returns how much living costs have changed over 5 years, using monthly medians for 81 cities from the MIC Retail Price Statistics Survey. It also explicitly distinguishes itself from suii_item by noting that item-level monthly data belongs to that sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete consultation triggers: 'how much was it 5 years ago', 'price increases', and 'price trends'. It also names the alternative suii_item for item-level monthly data, making the routing decision explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It conveys the data scope (68 months of monthly price readings) and implies a read-only lookup. It does not disclose the return format, the specific month range, units, or behavior for invalid codes, leaving moderate gaps for a data-retrieval tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, each earning its place: the first states the tool's purpose, the second explains code sourcing with a concrete example. The essential 'what' is front-loaded with zero filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter lookup with no output schema and no annotations, the purpose and input sourcing are adequately covered. The missing piece is the return shape (what fields come back, such as month and price) and the exact date range, which would help an agent interpret results but are not critical to invoking it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the schema merely declares item_code as a required string. The description compensates well by explaining that valid codes live in the suii list and giving a concrete example (米コシヒカリ5kg is 1001), adding meaning beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource and action: monthly prices per item over 68 months. It points to the suii master list for valid item codes, which distinguishes it from sibling 'item' tools (cost_item, lens_item, super_item) only partially — it doesn't explicitly name what differentiates it from them, but the '68 months' scope and suii-list reference give enough specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides one piece of usage direction: the item_code must come from the suii list, which tells the agent where to source valid inputs. However, it gives no explicit when-to-use vs. alternatives (e.g., when to prefer suii_item over cost_item or lens_item) and no exclusions. Guidance is present but minimal.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It states the tool returns a monthly series for a single item, which is a read operation. However, it does not disclose the response format, historical depth, or any error conditions. The basic behavioral fact (returning data) is present, but richer context like pagination or rate limits is absent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the main purpose and immediately useful examples. There is no wasted wording; every clause contributes to understanding what the tool does and how to use it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with a single parameter and no output schema, the description covers purpose, parameter examples, and the sibling tool for list retrieval. It does not describe the output structure, but given the simplicity and the pointer to super_pos, the essential context for calling the tool correctly is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does so by listing valid slug examples (eggs, milk, bread, etc.) and directing the user to super_pos for the full list. This gives the agent concrete guidance on parameter values beyond the bare string type, fully addressing the parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns a monthly series for one item of the supermarket price index, with a specific resource (Consumer Affairs Agency POS). It also gives concrete slug examples (eggs, milk, etc.) and distinguishes itself from super_pos, which provides the list of items. This is a specific verb+resource with clear sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly mentions the alternative: '一覧は super_pos で' (the list is in super_pos), telling the agent to use super_pos for the list and this tool for a specific item. It provides clear context for when to use this tool versus its sibling, though it doesn't enumerate other exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the behavioral disclosure burden. It usefully states the data source, national store coverage, item count, monthly frequency, and base period. It does not describe exact output columns or update lag, but for a no-parameter dataset this is reasonable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense, front-loaded Japanese sentence conveys the topic, source, store count, item count, base period, and examples with no filler or redundancy. Every element earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with no output schema, the description provides sufficient context: source, scope, metric definition, and representative items. There is no parameter risk, and the only minor gap is lack of detail on the returned result structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and the schema is trivially fully covered, so there is no parameter-level meaning for the description to add. Per calibration, zero parameters earns a baseline of 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource (supermarket prices), the specific data source (Consumer Affairs Agency POS, about 1,200 stores), the scope (26 items), and the metric (monthly index, Reiwa 7 average = 100). This clearly distinguishes it from data-lookup siblings like super_item or prices_now, despite not using an explicit verb.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage: an agent can infer it should be selected when supermarket price-index data is needed. However, it gives no explicit guidance about when to prefer this tool over siblings, nor does it mention excluded cases or alternative tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.